Linear and non-linear pattern recognition models for classification of fruit from visible–near infrared spectra

Kim, Jaesoo, Mowat, Alistair, Poole, Philip and Kasabov, Nikola (2000) Linear and non-linear pattern recognition models for classification of fruit from visible–near infrared spectra. Chemometrics and Intelligent Laboratory Systems, 51 2: 201-216. doi:10.1016/S0169-7439(00)00070-8


Author Kim, Jaesoo
Mowat, Alistair
Poole, Philip
Kasabov, Nikola
Title Linear and non-linear pattern recognition models for classification of fruit from visible–near infrared spectra
Journal name Chemometrics and Intelligent Laboratory Systems   Check publisher's open access policy
ISSN 0169-7439
Publication date 2000
Sub-type Article (original research)
DOI 10.1016/S0169-7439(00)00070-8
Volume 51
Issue 2
Start page 201
End page 216
Total pages 16
Editor D. L. Massart
O. M. Kualheim
P. D. Wentzell
Place of publication Amsterdam
Publisher Elsivier Science B.V
Collection year 2000
Language eng
Subject C1
280212 Neural Networks, Genetic Alogrithms and Fuzzy Logic
700102 Application tools and system utilities
Abstract Environment and genotype affect the composition, quality, storability and sensory properties of plant-based products. Visible-near infrared (NIR) spectral measurements are used increasingly to monitor fruit properties such as maturity, sensory properties and storability non-destructively both prior to harvest and during storage. To explore this problem, at harvest and after storage, visible-NIR spectra containing 1024 individual data points were measured on kiwifruit berries sourced from six pre-harvest fruit management treatments. These raw spectra were processed by principal component analysis (PCA), or by Fourier, Hartley, Haar, Hurst, range renormalisation or polar coordinate transforms (PCT) in order to extract a smaller set of features selected independently of treatment. In order to reduce their dimensionality further, the extracted features were processed by canonical variate analysis. The ability of various connectionist and linear discrimination pattern recognition models to predict the treatment source of unknown fruit on the basis of these features was evaluated. Thus far, this work has established that the performance of the non-linear model was shown to be significantly better in comparison to the linear model. From these results, it has also been shown that both the feature extraction and selection techniques have a marked effect on the ability to classify fruit by treatment source and storage date. In general, the best classifications were based on features extracted using the Fast Fourier Transform (FFT) method, but the best performance in any single classification was given by the Haar transform (HT) in conjunction with the scaled conjugated gradient learning method, (C) 2000 Elsevier Science B.V. All rights reserved.
Keyword Automation & Control Systems
Computer Science, Artificial Intelligence
Mathematics, Interdisciplinary Applications
Statistics & Probability
Chemistry, Analytical
Instruments & Instrumentation
Vnir Spectra
Kiwifruit
Linear Discrimination
Artificial Neural Networks
Feature Extraction
Pattern Recognition And Classification
Canonical Variate Analysis
Fast Hartley Transform
Neural Networks
Sugar Content
Spectroscopy
Convergence
Algorithm
Q-Index Code C1

Document type: Journal Article
Sub-type: Article (original research)
Collection: School of Agriculture and Food Sciences
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 46 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 54 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 10 Jun 2008, 12:26:53 EST